Related papers: Structure Tensor Representation for Robust Oriente…

This paper explores object detection in the small data regime, where only a limited number of annotated bounding boxes are available due to data rarity and annotation expense. This is a common challenge today with machine learning being…

3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations…

Fast appearance variations and the distractions of similar objects are two of the most challenging problems in visual object tracking. Unlike many existing trackers that focus on modeling only the target, in this work, we consider the…

SAR image classification naturally has to deal with huge noise and a high dynamic range particularly requiring robust classification models. Additionally, the deployment of these models on edge devices, such as drones and military aircraft,…

Anomaly detection in spatiotemporal data is a challenging problem encountered in a variety of applications, including video surveillance, medical imaging data, and urban traffic monitoring. Existing anomaly detection methods focus mainly on…

Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate representations as constraints to reduce the uncertainties and improve the consistencies between the 2D…

The development of efficient machine learning models for molecular systems representation is becoming crucial in scientific research. We introduce TensorNet, an innovative O(3)-equivariant message-passing neural network architecture that…

Predicting the structure of a protein from its sequence is a cornerstone task of molecular biology. Established methods in the field, such as homology modeling and fragment assembly, appeared to have reached their limit. However, this year…

Oriented object detection has been rapidly developed in the past few years, but most of these methods assume the training and testing images are under the same statistical distribution, which is far from reality. In this paper, we propose…

The representation theory of tensor functions is essential to constitutive modeling of materials including both mechanical and physical behaviors. Generally, material symmetry is incorporated in the tensor functions through a structural or…

Forward-looking sonar can capture high resolution images of underwater scenes, but their interpretation is complex. Generic object detection in such images has not been solved, specially in cases of small and unknown objects. In comparison,…

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a…

3D object detection aims to predict object centers, dimensions, and rotations from LiDAR point clouds. Despite its simplicity, LiDAR captures only the near side of objects, making center-based detectors prone to poor localization accuracy…

Deep learning for detecting objects in remotely sensed imagery can enable new technologies for important applications including mitigating climate change. However, these models often require large datasets labeled with bounding box…

We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the…

Point set registration is a powerful method that enables robots to manipulate deformable objects. By mapping the point cloud of the current object to the pre-trained point cloud, a transformation function can be constructed. The…

Tensor train (TT) decomposition is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. However, since the tensor product is not commutative, permutation of…

Detecting and localizing objects in space is a fundamental computer vision problem. While much progress has been made to solve 2D object detection, 3D object localization is much less explored and far from solved, especially for open-world…

Moving Object Detection (MOD) is a crucial task for the Autonomous Driving pipeline. MOD is usually handled via 2-stream convolutional architectures that incorporates both appearance and motion cues, without considering the inter-relations…

Sequential data such as time series, video, or text can be challenging to analyse as the ordered structure gives rise to complex dependencies. At the heart of this is non-commutativity, in the sense that reordering the elements of a…